INDEX

Explanations

date and time-related information

oai_token-act-pair · gpt-3.5-turbo

indicative phrases or metrics related to decision-making and consequences

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sucker

-0.84

 spitting

-0.78

 satell

-0.76

 neighb

-0.75

oun

-0.74

 therm

-0.74

 guts

-0.72

 torped

-0.72

 Liter

-0.70

 cens

-0.67

POSITIVE LOGITS

âĢ¢

1.79

Â·

1.53

âĹı

1.45

________________________________________________________________

1.39

âĸº

1.39

âĸł

1.38

-->

1.37

âĻ¦

1.36

Advertisements

1.35

________________________

1.34

Activations Density 0.235%

date and time-related information

indicative phrases or metrics related to decision-making and consequences

No Comments

No Known Activations